Estimation of fingertip forces using high-density surface electromyography

In this study, we propose a method to estimate the magnitude and direction of the forces exerted by a fingertip by measuring the muscle activity in the forearm using surface electromyography (sEMG). This approach will enable therapists to provide highly efficient rehabilitation programs to patients by tailoring exercises to the patient' s motor recovery status. However, estimating the magnitude and direction of the force exerted by a fingertip is difficult because deep muscles in the forearm, such as the deep flexor muscles, play an important role in the adjustment of the fingertip force, but the activity of deep muscles is difficult to measure because of the crosstalk between muscles. In this study, the force exerted by the fingertips is estimated from the activities of the forearm muscles measured by high-density sEMG which is modified by signal processing steps. To implement the estimation process, high-density sEMG sensors were placed on the right forearms of healthy participant and the activities of their forearm muscles were recorded. The index finger and the middle finger were fixed to a force sensor and the isometric forces of these fingers were simultaneously measured as the subjects sequentially applied forces in the palmar, distal, and dorsal directions. Then, it was demonstrated that the fingertip forces can be estimated by an artificial neural network based on the measured myoelectric potentials with applied signal processing.